Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Vishal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िक
    1.17
    вших
    1.17
    ри
    1.16
    siniz
    1.08
     imaginable
    1.08
     divisible
    1.07
     densely
    1.06
    üedad
    1.06
    ﻞ
    1.05
     zirconia
    1.05
    POSITIVE LOGITS
    il
    1.16
    I
    1.13
    en
    1.03
    ay
    1.01
    n
    0.99
     Ở
    0.96
    COVID
    0.96
    á
    0.95
     อยาก
    0.94
     Còn
    0.94
    Act Density 0.378%

    No Known Activations